A plugin marketplace entry for Jeff, a workflow protocol for trusted operators and cooperating agents. It describes Jeff as a quality-control layer, not a security sandbox.

Use it to package or publish the Jeff plugin in a marketplace listing.

The listing tells a marketplace how to identify and describe the Jeff plugin. It also sets the expectation that Jeff coordinates quality checks rather than isolating untrusted code.

jeff — Plugin by johanthoren

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add johanthoren/jeff

agentmods

npx agentmods add plugins/johanthoren/jeff/marketplace

Clone the repo

git clone --depth 1 https://github.com/johanthoren/jeff

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

jeff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/marketplace.json · 12 lines

What it actually says

{
  "name": "jeff",
  "owner": { "name": "Johan Thorén" },
  "plugins": [
    {
      "name": "jeff",
      "source": "./",
      "description": "Your sous chef, Jeff: a model-native quality control plane and cooperative workflow protocol for trusted operators and friendly agents, not a security sandbox."
    }
  ]
}

Files

What ships with it

1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

plugin.json 528 B

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 12 lines scan A b5d02f1001fa

Subscribe to this mod's changes

jeff is a plugin published in the GitHub repository johanthoren/jeff (4 stars, last pushed 5d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Productivity Security agentic-ai claude-code claude-code-plugin claude-skills

agent-teams

Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams.

wshobson/agents · not measured

wt-local

Local marketplace populated by wta.

microsoft/intelligent-terminal · not measured

antimicrobial-resistance-scientist

Reasons from MIC distributions, ECOFFs, and phenotype–genotype concordance through EUCAST/CLSI AST, CARD/RGI and AMRFinderPlus resistomes, GLASS/WHONET/NARMS surveillance, carbapenemase/ESBL/MRSA mechanism panels, and heteroresistance PAP while treating breakpoint mixing, genotype-without-phenotype overclaim…

K-Dense-AI/scientific-agents · not measured

moraine

Claude Code plugin for Moraine MCP session search, realtime agent awareness, and sanitized bug reports.

eric-tramel/moraine · not measured

ainb-hooks

Emit every safely observable Claude Code lifecycle event into Hangar's durable provider log. User-facing events still reach ainb-notifyd over its Unix socket. The same notify.sh powers ATC structured control when installed with AINBMANAGED=atc. stallguard.py additionally blocks turn-end when a session would idle on i.

stevengonsalvez/agents-in-a-box · not measured

rudder

Maintain a device-local spec from coding-session intent, then generate focused unit tests with your existing coding agent.

RudderCode/Rudder · not measured